[스크랩] NVIDIA Research Turns 2D Photos Into 3D Scenes in the Blink of an AI

원문 : https://nvlabs.github.io/instant-ngp/

Abstract

---

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations. A small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of 1920x1080.

 

 

<시연영상>

 

관련 논문 :

mueller2022instant.pdf

16.73MB

https://unsplash.com/photos/4N8oM5L7hyM